Triple
T22403685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nagraj Manjule |
E553825
|
entity |
| Predicate | directorOf |
P537
|
FINISHED |
| Object | Fandry |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Fandry | Statement: [Nagraj Manjule, directorOf, Fandry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fandry Context triple: [Nagraj Manjule, directorOf, Fandry]
-
A.
Fandry
chosen
Fandry is a critically acclaimed Marathi-language film that powerfully portrays caste discrimination and social injustice in rural India.
-
B.
Starcross
Starcross is a small village and railway stop on the Exe Estuary in Devon, England, known for its scenic coastal setting and historic transport links.
-
C.
Fárrago
Fárrago is a celebrated poetry collection by Colombian writer León de Greiff, known for its rich language, erudite allusions, and playful, experimental style.
-
D.
Fainall
Fainall is a central, scheming antagonist in William Congreve’s Restoration comedy "The Way of the World," known for his manipulative and duplicitous nature.
-
E.
Figment
Figment is a small purple dragon from Disney's Epcot theme park, known as the playful embodiment of imagination in the Journey Into Imagination attraction.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158b6762c8190991fc14c5ca8e609 |
completed | April 29, 2026, 1:02 a.m. |
Created at: April 16, 2026, 8:46 p.m.